arrow
返回

Machine Learning-Assisted Quasi-Bisection Method for Pixelated Patch Antenna Bandwidth Optimization

delete2024-12-01
delete0
PRE
AI
Q
Qipeng Wang *
Z
Zhongxuan Pang
D
Di Gao
P
Peng Liu
X
Xiaoyu Pang
殷
殷晓星 (Xiaoxing Yin)
DOI:10.1109/LAWP.2024.3475628delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
A machine learning-assisted quasi-bisection method (MLAQBM) is proposed for the broadband optimization of the pixelated patch antennas. Distinct from traditional MLA optimization methods, MLAQBM employs a coarse-to-fine pixel partition and machine learning optimization to iteratively refine the shape of the antenna. Two implementation strategies are introduced. In the first strategy, larger pixels are initially partitioned and samples are collected. A surrogate model is then established using convolutional neural networks (CNN), and an initial shape is derived through particle swarm optimization (PSO). Again, further refinement is achieved by finer pixel partitioning and subsequent CNN-based PSO. The second strategy leverages a pre-existing broadband E-shaped patch design, which is then subdivided into smaller pixels. By collecting samples, training a CNN surrogate model, and performing PSO optimization, a broader bandwidth is realized. Compared with the reported MLA optimization methods, MLAQBM establishes a stable surrogate model that is robust, easy to converge, and adaptable to different optimization objectives. To validate the proposed strategies, the optimized pixelated patch antennas are fabricated and measured. The measured results demonstrate that the bandwidth of the proposed patch antennas achieves 24.5% and 32.5%.
Keyword:
Optimization
Patch antennas
Image quality
Training
Convolutional neural networks
Bandwidth
Reflection coefficient
Broadband antennas
Antennas
Predictive models
convolutional neural network (CNN)
machine learning
particle swarm optimization (PSO)
pixel
quasi-bisection method

期刊

IEEE Antennas and Wireless Propagation Letters 封面图
IEEE Antennas and Wireless Propagation Letters
IF:
4.8
论文数:
1.0W
被引数:
2.8W

机构

S
southeast university - china
学者数:
5.3W
论文数: 4.9W
被引数: 57
引用论文

引用论文

Design and Optimization of a High-Gain Filtering Antenna Based on Parasitic Pixel Layer
err2023-05-01
err5
PREAI
errPeng, Fan; Liao, Cheng; Cheng, You-Feng; Feng, Ju; Mo, Xiao-Wei; Ding, Xiao
err分享
err收藏
err分享
err收藏
MICROSTRIP ANTENNAS
err1992-01-01
err708
PREAI
errPOZAR, DM
err分享
err收藏
Calcium channel blockers for antipsychotic-induced tardive dyskinesia
err2018-03-26
err0
errOAAI
errAdib Essali; Karla Soares-Weiser; Hanna Bergman; Clive E Adams
err分享
err收藏
Cross-Entropy Method for Design and Optimization of Pixelated Metasurfaces
err2020-01-01
err10
errOAAI
errKovaleva, Maria; Bulger, David; Esselle, Karu P.
err分享
err收藏
学者 查看更多内容